Multi-Sender Persuasion: A Computational Perspective

Safwan Hossain, Tonghan Wang, Tao Lin, Yiling Chen, David C. Parkes, Haifeng Xu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18944-18971, 2024.

Abstract

We consider multiple senders with informational advantage signaling to convince a single self-interested actor to take certain actions. Generalizing the seminal Bayesian Persuasion framework, such settings are ubiquitous in computational economics, multi-agent learning, and machine learning with multiple objectives. The core solution concept here is the Nash equilibrium of senders’ signaling policies. Theoretically, we prove that finding an equilibrium in general is PPAD-Hard; in fact, even computing a sender’s best response is NP-Hard. Given these intrinsic difficulties, we turn to finding local Nash equilibria. We propose a novel differentiable neural network to approximate this game’s non-linear and discontinuous utilities. Complementing this with the extra-gradient algorithm, we discover local equilibria that Pareto dominates full-revelation equilibria and those found by existing neural networks. Broadly, our theoretical and empirical contributions are of interest to a large class of economic problems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-hossain24c, title = {Multi-Sender Persuasion: A Computational Perspective}, author = {Hossain, Safwan and Wang, Tonghan and Lin, Tao and Chen, Yiling and Parkes, David C. and Xu, Haifeng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {18944--18971}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/hossain24c/hossain24c.pdf}, url = {https://proceedings.mlr.press/v235/hossain24c.html}, abstract = {We consider multiple senders with informational advantage signaling to convince a single self-interested actor to take certain actions. Generalizing the seminal Bayesian Persuasion framework, such settings are ubiquitous in computational economics, multi-agent learning, and machine learning with multiple objectives. The core solution concept here is the Nash equilibrium of senders’ signaling policies. Theoretically, we prove that finding an equilibrium in general is PPAD-Hard; in fact, even computing a sender’s best response is NP-Hard. Given these intrinsic difficulties, we turn to finding local Nash equilibria. We propose a novel differentiable neural network to approximate this game’s non-linear and discontinuous utilities. Complementing this with the extra-gradient algorithm, we discover local equilibria that Pareto dominates full-revelation equilibria and those found by existing neural networks. Broadly, our theoretical and empirical contributions are of interest to a large class of economic problems.} }
Endnote
%0 Conference Paper %T Multi-Sender Persuasion: A Computational Perspective %A Safwan Hossain %A Tonghan Wang %A Tao Lin %A Yiling Chen %A David C. Parkes %A Haifeng Xu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-hossain24c %I PMLR %P 18944--18971 %U https://proceedings.mlr.press/v235/hossain24c.html %V 235 %X We consider multiple senders with informational advantage signaling to convince a single self-interested actor to take certain actions. Generalizing the seminal Bayesian Persuasion framework, such settings are ubiquitous in computational economics, multi-agent learning, and machine learning with multiple objectives. The core solution concept here is the Nash equilibrium of senders’ signaling policies. Theoretically, we prove that finding an equilibrium in general is PPAD-Hard; in fact, even computing a sender’s best response is NP-Hard. Given these intrinsic difficulties, we turn to finding local Nash equilibria. We propose a novel differentiable neural network to approximate this game’s non-linear and discontinuous utilities. Complementing this with the extra-gradient algorithm, we discover local equilibria that Pareto dominates full-revelation equilibria and those found by existing neural networks. Broadly, our theoretical and empirical contributions are of interest to a large class of economic problems.
APA
Hossain, S., Wang, T., Lin, T., Chen, Y., Parkes, D.C. & Xu, H.. (2024). Multi-Sender Persuasion: A Computational Perspective. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:18944-18971 Available from https://proceedings.mlr.press/v235/hossain24c.html.

Related Material